Reanalysis of the Bridge et al. study of suicide following release of 13 Reasons Why

Abstract

Bridge et al. recently presented a time series analysis of suicide rates in the US following the release of the 2017 Netflix series "13 Reasons Why." Their analysis found a powerful effect of the show on boys ages 10-17 for nine months after the show was released in April 2017. I questioned this finding on two grounds. First, contagion would be expected to be stronger for girls than boys for this story, and second their analysis did not take into account strong secular trends in suicide, especially in boys from 2016 to 2017. I reanalyzed their data using a simple auto-regression model that tested for changes in rates after removing auto-correlation and national trends in suicide. I found that the increase for boys observed by Bridge et al. in April was no greater than the increase observed during the prior month before the show was released. There were also no effects in later months of that year. For girls, I found a small but nonsignificant increase in suicide in April that was unique to that month, potentially consistent with a combined protective and harmful effect of the show. In total, I conclude that it is difficult to attribute harmful effects of the show using aggregate rates of monthly suicide rates. More fine-grained analyses at the weekly level may be more valid but only after controlling for secular changes in suicide that have been particularly strong since 2008 in the US.

Fig 1. Suicide rates per 100,000 in youth ages 15–19 in the US, 1981–2017.

Source: CDC.

Fig 2. Time series from January 2013 to December 2017 after removal of linear and quadratic trends and autocorrelation in suicide for boys ages 10–17 with month 52 (April of 2017) referenced.

Fig 3. Time series from January 2013 to December 2017 after removal of linear trend in suicide for girls ages 10–17 with month 52 (April of 2017) referenced.